國立高雄大學圖資館 |

Language: English

Back

Learning Grammar of Complex Activities via Deep Neural Networks.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Learning Grammar of Complex Activities via Deep Neural Networks.
Author:	Mashaido, Becky.
Published:	Ann Arbor : ProQuest Dissertations & Theses, 2022
Description:	8 p.
Notes:	Source: Masters Abstracts International, Volume: 82-09.
Notes:	Advisor: Elhamifar, Ehsan.
Contained By:	Masters Abstracts International82-09.
Subject:	Computer science.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28264699
ISBN:	9798582503200

Learning Grammar of Complex Activities via Deep Neural Networks.
Mashaido, Becky.

Learning Grammar of Complex Activities via Deep Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 8 p.

Source: Masters Abstracts International, Volume: 82-09.

Thesis (M.S.)--Northeastern University, 2022.

This item must not be sold to any third party vendors.

Motivated by the growing amount of publicly available video data on online streaming services and an increased interest in applications that analyze continuous video streams such as autonomous driving, this technical report provides a theoretical insight into deep neural networks for video learning, under label constraints. I build upon previous work in video learning for computer vision, make observations on model performance and propose further mechanisms to help improve our observations.

ISBN: 9798582503200Subjects--Topical Terms:

199325
Computer science.
Subjects--Index Terms:

Complex activities

Learning Grammar of Complex Activities via Deep Neural Networks.
LDR:01570nmm a2200349 4500 001 616394
005 20220513114325.5
008 220920s2022 ||||||||||||||||| ||eng d
020 $a 9798582503200
035 $a (MiAaPQ)AAI28264699
035 $a AAI28264699
040 $a MiAaPQ $c MiAaPQ
100 1 $a Mashaido, Becky. $3 915570
245 1 0 $a Learning Grammar of Complex Activities via Deep Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 8 p.
500 $a Source: Masters Abstracts International, Volume: 82-09.
500 $a Advisor: Elhamifar, Ehsan.
502 $a Thesis (M.S.)--Northeastern University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Motivated by the growing amount of publicly available video data on online streaming services and an increased interest in applications that analyze continuous video streams such as autonomous driving, this technical report provides a theoretical insight into deep neural networks for video learning, under label constraints. I build upon previous work in video learning for computer vision, make observations on model performance and propose further mechanisms to help improve our observations.
590 $a School code: 0160.
650 4 $a Computer science. $3 199325
650 4 $a Information science. $3 190425
653 $a Complex activities
653 $a Deep Neural Networks
653 $a Online streaming
653 $a Computer vision
690 $a 0984
690 $a 0723
710 2 $a Northeastern University. $b Computer Science. $3 915571
773 0 $t Masters Abstracts International $g 82-09.
790 $a 0160
791 $a M.S.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28264699